Чётко очерченная руководящая роль в ведущей AI-лаборатории с большим влиянием на безопасность ИИ и широким взаимодействием между командами; узкая специализация и высокий уровень ответственности требуют серьёзного опыта в этой области.
?Узкая специализация
Актуальные технологии
Большой вклад
Сильная AI-лаборатория
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Research Engineering Manager, Responsible Frontier AI Research, DeepMind (AI Safety): Leading engineering teams building automated red-teaming platforms, jailbreak discovery systems, safety evaluations, agent defenses, and mitigation pipelines with an accent on responsible frontier AI research and scalable infrastructure. Focus on setting technical roadmaps, evolving evaluation and mitigation systems for increasingly capable multimodal agents, and solving secure, reliable engineering challenges for sensitive safety research.
Location: London, UK
Company
Google DeepMind is an AI research lab developing advanced technologies for scientific discovery, product innovation, and public benefit, with safety and ethics as core priorities.
What you will do
Lead a team of Research and Software Engineers building engineering foundations for responsible frontier AI research.
Set priorities across multiple workstreams and move engineering capacity as research priorities change.
Define technical roadmaps for evaluation pipelines, red-teaming tools, autoraters, and mitigation training pipelines.
Oversee system design and code reviews, establishing practices for code quality, scalability, reliability, and secure handling of sensitive data.
Hire, develop, coach, and retain a high-performing engineering team.
Partner with Research, Product, Policy, Trust and Safety, and subject-matter experts to turn research into evaluations and mitigations that inform model launch decisions.
Requirements
Experience leading teams working on AI safety, security, or responsible AI research, including areas such as adversarial robustness, red teaming, safety evaluations, or mitigations for frontier models.
Experience with one or more of: automated red teaming or jailbreak discovery; LLM-based autoraters and evaluation design; safety classifiers or probes; prompt injection and agent security; or evaluation of severe-harm risks such as CBRN and harmful manipulation.
Nice to have
Master’s degree or PhD in Engineering, Computer Science, or a related technical field focused on adversarial machine learning or AI/ML security.
Research or engineering achievements such as peer-reviewed publications, open-source projects, or public benchmarks.
Culture & Benefits
Work within a specialized Applied Research and Responsibility team integrated with DeepMind and partnered across Google.
Collaborate with interdisciplinary and global teams across Research, Product, Policy, and Trust and Safety.
Support AI development focused on safety, ethics, scientific discovery, and broad public benefit.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →